Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

c54b245d · Linus Torvalds <[email protected]> · 2021-06-28 20:39:26 -07:00

Pull user namespace rlimit handling update from Eric Biederman:
 "This is the work mainly by Alexey Gladkov to limit rlimits to the
  rlimits of the user that created a user namespace, and to allow users
  to have stricter limits on the resources created within a user
  namespace."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  cred: add missing return error code when set_cred_ucounts() failed
  ucounts: Silence warning in dec_rlimit_ucounts
  ucounts: Set ucount_max to the largest positive value the type can hold
  kselftests: Add test to check for rlimit changes in different user namespaces
  Reimplement RLIMIT_MEMLOCK on top of ucounts
  Reimplement RLIMIT_SIGPENDING on top of ucounts
  Reimplement RLIMIT_MSGQUEUE on top of ucounts
  Reimplement RLIMIT_NPROC on top of ucounts
  Use atomic_t for ucounts reference counting
  Add a reference to ucounts for each cred
  Increase size of ucounts to atomic_long_t

Commit: c54b245d011855ea91c5beff07f1db74143ce614
Parents: e17c120f · 5e6b8a50

Merge commit. Changes below are compared with the first parent: e17c120f.

Changes

29 files changed · +468 −127

File	Status	Add	Del	Content
fs/exec.c	modified	+5	−1	View file
fs/hugetlbfs/inode.c	modified	+8	−8	View file
fs/proc/array.c	modified	+1	−1	View file
include/linux/cred.h	modified	+4	−0	View file
include/linux/hugetlb.h	modified	+2	−2	View file
include/linux/mm.h	modified	+2	−2	View file
include/linux/sched/user.h	modified	+0	−7	View file
include/linux/shmem_fs.h	modified	+1	−1	View file
include/linux/signal_types.h	modified	+3	−1	View file
include/linux/user_namespace.h	modified	+28	−3	View file
ipc/mqueue.c	modified	+21	−19	View file
ipc/shm.c	modified	+13	−13	View file
kernel/cred.c	modified	+46	−5	View file
kernel/exit.c	modified	+1	−1	View file
kernel/fork.c	modified	+14	−4	View file
kernel/signal.c	modified	+13	−12	View file
kernel/sys.c	modified	+13	−1	View file
kernel/ucount.c	modified	+91	−25	View file
kernel/user.c	modified	+0	−3	View file
kernel/user_namespace.c	modified	+8	−1	View file
mm/memfd.c	modified	+2	−2	View file
mm/mlock.c	modified	+14	−8	View file
mm/mmap.c	modified	+2	−2	View file
mm/shmem.c	modified	+5	−5	View file
tools/testing/selftests/Makefile	modified	+1	−0	View file
tools/testing/selftests/rlimits/.gitignore	added	+2	−0	View file
tools/testing/selftests/rlimits/Makefile	added	+6	−0	View file
tools/testing/selftests/rlimits/config	added	+1	−0	View file
tools/testing/selftests/rlimits/rlimits-per-userns.c	added	+161	−0	View file

Only the first 600 diff lines are shown. Download the complete patch.

fs/exec.c

View file

diff --git a/fs/exec.c b/fs/exec.c
index 18594f1..f2bcdbe 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1360,6 +1360,10 @@ int begin_new_exec(struct linux_binprm * bprm)
 	WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1);
 	flush_signal_handlers(me, 0);
 
+	retval = set_cred_ucounts(bprm->cred);
+	if (retval < 0)
+		goto out_unlock;
+
 	/*
 	 * install the new credentials for this executable
 	 */
@@ -1874,7 +1878,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * whether NPROC limit is still exceeded.
 	 */
 	if ((current->flags & PF_NPROC_EXCEEDED) &&
-	    atomic_read(&current_user()->processes) > rlimit(RLIMIT_NPROC)) {
+	    is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		retval = -EAGAIN;
 		goto out_ret;
 	}

fs/hugetlbfs/inode.c

View file

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 30dee68..926eeb9 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1446,7 +1446,7 @@ static int get_hstate_idx(int page_size_log)
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
  */
 struct file *hugetlb_file_setup(const char *name, size_t size,
-				vm_flags_t acctflag, struct user_struct **user,
+				vm_flags_t acctflag, struct ucounts **ucounts,
 				int creat_flags, int page_size_log)
 {
 	struct inode *inode;
@@ -1458,20 +1458,20 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
-	*user = NULL;
+	*ucounts = NULL;
 	mnt = hugetlbfs_vfsmount[hstate_idx];
 	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
-		*user = current_user();
-		if (user_shm_lock(size, *user)) {
+		*ucounts = current_ucounts();
+		if (user_shm_lock(size, *ucounts)) {
 			task_lock(current);
 			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
 				current->comm, current->pid);
 			task_unlock(current);
 		} else {
-			*user = NULL;
+			*ucounts = NULL;
 			return ERR_PTR(-EPERM);
 		}
 	}
@@ -1498,9 +1498,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 
 	iput(inode);
 out:
-	if (*user) {
-		user_shm_unlock(size, *user);
-		*user = NULL;
+	if (*ucounts) {
+		user_shm_unlock(size, *ucounts);
+		*ucounts = NULL;
 	}
 	return file;
 }

fs/proc/array.c

View file

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 7ec5917..ee0ce8c 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -284,7 +284,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
 		collect_sigign_sigcatch(p, &ignored, &caught);
 		num_threads = get_nr_threads(p);
 		rcu_read_lock();  /* FIXME: is this correct? */
-		qsize = atomic_read(&__task_cred(p)->user->sigpending);
+		qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
 		rcu_read_unlock();
 		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
 		unlock_task_sighand(p, &flags);

include/linux/cred.h

View file

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 1497132..fcbc688 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -143,6 +143,7 @@ struct cred {
 #endif
 	struct user_struct *user;	/* real user ID subscription */
 	struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
+	struct ucounts *ucounts;
 	struct group_info *group_info;	/* supplementary groups for euid/fsgid */
 	/* RCU deletion */
 	union {
@@ -169,6 +170,7 @@ extern int set_security_override_from_ctx(struct cred *, const char *);
 extern int set_create_files_as(struct cred *, struct inode *);
 extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
+extern int set_cred_ucounts(struct cred *);
 
 /*
  * check for validity of credentials
@@ -369,6 +371,7 @@ static inline void put_cred(const struct cred *_cred)
 
 #define task_uid(task)		(task_cred_xxx((task), uid))
 #define task_euid(task)		(task_cred_xxx((task), euid))
+#define task_ucounts(task)	(task_cred_xxx((task), ucounts))
 
 #define current_cred_xxx(xxx)			\
 ({						\
@@ -385,6 +388,7 @@ static inline void put_cred(const struct cred *_cred)
 #define current_fsgid() 	(current_cred_xxx(fsgid))
 #define current_cap()		(current_cred_xxx(cap_effective))
 #define current_user()		(current_cred_xxx(user))
+#define current_ucounts()	(current_cred_xxx(ucounts))
 
 extern struct user_namespace init_user_ns;
 #ifdef CONFIG_USER_NS

include/linux/hugetlb.h

View file

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3c01176..8ba79dc 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -451,7 +451,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
-				struct user_struct **user, int creat_flags,
+				struct ucounts **ucounts, int creat_flags,
 				int page_size_log);
 
 static inline bool is_file_hugepages(struct file *file)
@@ -471,7 +471,7 @@ static inline struct hstate *hstate_inode(struct inode *i)
 #define is_file_hugepages(file)			false
 static inline struct file *
 hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
-		struct user_struct **user, int creat_flags,
+		struct ucounts **ucounts, int creat_flags,
 		int page_size_log)
 {
 	return ERR_PTR(-ENOSYS);

include/linux/mm.h

View file

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8ae3162..01ecf9e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1709,8 +1709,8 @@ extern bool can_do_mlock(void);
 #else
 static inline bool can_do_mlock(void) { return false; }
 #endif
-extern int user_shm_lock(size_t, struct user_struct *);
-extern void user_shm_unlock(size_t, struct user_struct *);
+extern int user_shm_lock(size_t, struct ucounts *);
+extern void user_shm_unlock(size_t, struct ucounts *);
 
 /*
  * Parameter block passed down to zap_pte_range in exceptional cases.

include/linux/sched/user.h

View file

diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 3632c5d..2462f7d 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -12,16 +12,9 @@
  */
 struct user_struct {
 	refcount_t __count;	/* reference count */
-	atomic_t processes;	/* How many processes does this user have? */
-	atomic_t sigpending;	/* How many pending signals does this user have? */
 #ifdef CONFIG_EPOLL
 	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
-#ifdef CONFIG_POSIX_MQUEUE
-	/* protected by mq_lock	*/
-	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
-#endif
-	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 

include/linux/shmem_fs.h

View file

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index d82b6f3..aa77dcd 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -65,7 +65,7 @@ extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
-extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts);
 #ifdef CONFIG_SHMEM
 extern const struct address_space_operations shmem_aops;
 static inline bool shmem_mapping(struct address_space *mapping)

include/linux/signal_types.h

View file

diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index 68e06c7..34cb28b 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -13,6 +13,8 @@ typedef struct kernel_siginfo {
 	__SIGINFO;
 } kernel_siginfo_t;
 
+struct ucounts;
+
 /*
  * Real Time signals may be queued.
  */
@@ -21,7 +23,7 @@ struct sigqueue {
 	struct list_head list;
 	int flags;
 	kernel_siginfo_t info;
-	struct user_struct *user;
+	struct ucounts *ucounts;
 };
 
 /* flags values. */

include/linux/user_namespace.h

View file

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 1d08dbb..eb70cab 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -54,9 +54,15 @@ enum ucount_type {
 	UCOUNT_FANOTIFY_GROUPS,
 	UCOUNT_FANOTIFY_MARKS,
 #endif
+	UCOUNT_RLIMIT_NPROC,
+	UCOUNT_RLIMIT_MSGQUEUE,
+	UCOUNT_RLIMIT_SIGPENDING,
+	UCOUNT_RLIMIT_MEMLOCK,
 	UCOUNT_COUNTS,
 };
 
+#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -92,23 +98,42 @@ struct user_namespace {
 	struct ctl_table_header *sysctls;
 #endif
 	struct ucounts		*ucounts;
-	int ucount_max[UCOUNT_COUNTS];
+	long ucount_max[UCOUNT_COUNTS];
 } __randomize_layout;
 
 struct ucounts {
 	struct hlist_node node;
 	struct user_namespace *ns;
 	kuid_t uid;
-	int count;
-	atomic_t ucount[UCOUNT_COUNTS];
+	atomic_t count;
+	atomic_long_t ucount[UCOUNT_COUNTS];
 };
 
 extern struct user_namespace init_user_ns;
+extern struct ucounts init_ucounts;
 
 bool setup_userns_sysctls(struct user_namespace *ns);
 void retire_userns_sysctls(struct user_namespace *ns);
 struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type);
 void dec_ucount(struct ucounts *ucounts, enum ucount_type type);
+struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid);
+struct ucounts * __must_check get_ucounts(struct ucounts *ucounts);
+void put_ucounts(struct ucounts *ucounts);
+
+static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type)
+{
+	return atomic_long_read(&ucounts->ucount[type]);
+}
+
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
+
+static inline void set_rlimit_ucount_max(struct user_namespace *ns,
+		enum ucount_type type, unsigned long max)
+{
+	ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX;
+}
 
 #ifdef CONFIG_USER_NS
 

ipc/mqueue.c

View file

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 4e4e611..5becca9 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -144,7 +144,7 @@ struct mqueue_inode_info {
 	struct pid *notify_owner;
 	u32 notify_self_exec_id;
 	struct user_namespace *notify_user_ns;
-	struct user_struct *user;	/* user who created, for accounting */
+	struct ucounts *ucounts;	/* user who created, for accounting */
 	struct sock *notify_sock;
 	struct sk_buff *notify_cookie;
 
@@ -292,7 +292,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 		struct ipc_namespace *ipc_ns, umode_t mode,
 		struct mq_attr *attr)
 {
-	struct user_struct *u = current_user();
 	struct inode *inode;
 	int ret = -ENOMEM;
 
@@ -321,7 +320,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 		info->notify_owner = NULL;
 		info->notify_user_ns = NULL;
 		info->qsize = 0;
-		info->user = NULL;	/* set when all is ok */
+		info->ucounts = NULL;	/* set when all is ok */
 		info->msg_tree = RB_ROOT;
 		info->msg_tree_rightmost = NULL;
 		info->node_cache = NULL;
@@ -371,19 +370,23 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 		if (mq_bytes + mq_treesize < mq_bytes)
 			goto out_inode;
 		mq_bytes += mq_treesize;
-		spin_lock(&mq_lock);
-		if (u->mq_bytes + mq_bytes < u->mq_bytes ||
-		    u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
+		info->ucounts = get_ucounts(current_ucounts());
+		if (info->ucounts) {
+			long msgqueue;
+
+			spin_lock(&mq_lock);
+			msgqueue = inc_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
+			if (msgqueue == LONG_MAX || msgqueue > rlimit(RLIMIT_MSGQUEUE)) {
+				dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
+				spin_unlock(&mq_lock);
+				put_ucounts(info->ucounts);
+				info->ucounts = NULL;
+				/* mqueue_evict_inode() releases info->messages */
+				ret = -EMFILE;
+				goto out_inode;
+			}
 			spin_unlock(&mq_lock);
-			/* mqueue_evict_inode() releases info->messages */
-			ret = -EMFILE;
-			goto out_inode;
 		}
-		u->mq_bytes += mq_bytes;
-		spin_unlock(&mq_lock);
-
-		/* all is ok */
-		info->user = get_uid(u);
 	} else if (S_ISDIR(mode)) {
 		inc_nlink(inode);
 		/* Some things misbehave if size == 0 on a directory */
@@ -497,7 +500,6 @@ static void mqueue_free_inode(struct inode *inode)
 static void mqueue_evict_inode(struct inode *inode)
 {
 	struct mqueue_inode_info *info;
-	struct user_struct *user;
 	struct ipc_namespace *ipc_ns;
 	struct msg_msg *msg, *nmsg;
 	LIST_HEAD(tmp_msg);
@@ -520,8 +522,7 @@ static void mqueue_evict_inode(struct inode *inode)
 		free_msg(msg);
 	}
 
-	user = info->user;
-	if (user) {
+	if (info->ucounts) {
 		unsigned long mq_bytes, mq_treesize;
 
 		/* Total amount of bytes accounted for the mqueue */
@@ -533,7 +534,7 @@ static void mqueue_evict_inode(struct inode *inode)
 					  info->attr.mq_msgsize);
 
 		spin_lock(&mq_lock);
-		user->mq_bytes -= mq_bytes;
+		dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
 		/*
 		 * get_ns_from_inode() ensures that the
 		 * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
@@ -543,7 +544,8 @@ static void mqueue_evict_inode(struct inode *inode)
 		if (ipc_ns)
 			ipc_ns->mq_queues_count--;
 		spin_unlock(&mq_lock);
-		free_uid(user);
+		put_ucounts(info->ucounts);
+		info->ucounts = NULL;
 	}
 	if (ipc_ns)
 		put_ipc_ns(ipc_ns);

ipc/shm.c

View file

diff --git a/ipc/shm.c b/ipc/shm.c
index febd88d..003234f 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -60,7 +60,7 @@ struct shmid_kernel /* private to the kernel */
 	time64_t		shm_ctim;
 	struct pid		*shm_cprid;
 	struct pid		*shm_lprid;
-	struct user_struct	*mlock_user;
+	struct ucounts		*mlock_ucounts;
 
 	/* The task created the shm object.  NULL if the task is dead. */
 	struct task_struct	*shm_creator;
@@ -286,10 +286,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_rmid(ns, shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
-		shmem_lock(shm_file, 0, shp->mlock_user);
-	else if (shp->mlock_user)
+		shmem_lock(shm_file, 0, shp->mlock_ucounts);
+	else if (shp->mlock_ucounts)
 		user_shm_unlock(i_size_read(file_inode(shm_file)),
-				shp->mlock_user);
+				shp->mlock_ucounts);
 	fput(shm_file);
 	ipc_update_pid(&shp->shm_cprid, NULL);
 	ipc_update_pid(&shp->shm_lprid, NULL);
@@ -625,7 +625,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	shp->shm_perm.key = key;
 	shp->shm_perm.mode = (shmflg & S_IRWXUGO);
-	shp->mlock_user = NULL;
+	shp->mlock_ucounts = NULL;
 
 	shp->shm_perm.security = NULL;
 	error = security_shm_alloc(&shp->shm_perm);
@@ -650,7 +650,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
 		file = hugetlb_file_setup(name, hugesize, acctflag,
-				  &shp->mlock_user, HUGETLB_SHMFS_INODE,
+				  &shp->mlock_ucounts, HUGETLB_SHMFS_INODE,
 				(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
 	} else {
 		/*
@@ -698,8 +698,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 no_id:
 	ipc_update_pid(&shp->shm_cprid, NULL);
 	ipc_update_pid(&shp->shm_lprid, NULL);
-	if (is_file_hugepages(file) && shp->mlock_user)
-		user_shm_unlock(size, shp->mlock_user);
+	if (is_file_hugepages(file) && shp->mlock_ucounts)
+		user_shm_unlock(size, shp->mlock_ucounts);
 	fput(file);
 	ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
 	return error;
@@ -1105,12 +1105,12 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
 		goto out_unlock0;
 
 	if (cmd == SHM_LOCK) {
-		struct user_struct *user = current_user();
+		struct ucounts *ucounts = current_ucounts();
 
-		err = shmem_lock(shm_file, 1, user);
+		err = shmem_lock(shm_file, 1, ucounts);
 		if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
 			shp->shm_perm.mode |= SHM_LOCKED;
-			shp->mlock_user = user;
+			shp->mlock_ucounts = ucounts;
 		}
 		goto out_unlock0;
 	}
@@ -1118,9 +1118,9 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
 	/* SHM_UNLOCK */
 	if (!(shp->shm_perm.mode & SHM_LOCKED))
 		goto out_unlock0;
-	shmem_lock(shm_file, 0, shp->mlock_user);
+	shmem_lock(shm_file, 0, shp->mlock_ucounts);
 	shp->shm_perm.mode &= ~SHM_LOCKED;
-	shp->mlock_user = NULL;
+	shp->mlock_ucounts = NULL;
 	get_file(shm_file);
 	ipc_unlock_object(&shp->shm_perm);
 	rcu_read_unlock();

kernel/cred.c

View file

diff --git a/kernel/cred.c b/kernel/cred.c
index e1d274c..e6fd2b3 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -60,6 +60,7 @@ struct cred init_cred = {
 	.user			= INIT_USER,
 	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
+	.ucounts		= &init_ucounts,
 };
 
 static inline void set_cred_subscribers(struct cred *cred, int n)
@@ -119,6 +120,8 @@ static void put_cred_rcu(struct rcu_head *rcu)
 	if (cred->group_info)
 		put_group_info(cred->group_info);
 	free_uid(cred->user);
+	if (cred->ucounts)
+		put_ucounts(cred->ucounts);
 	put_user_ns(cred->user_ns);
 	kmem_cache_free(cred_jar, cred);
 }
@@ -222,6 +225,7 @@ struct cred *cred_alloc_blank(void)
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	new->magic = CRED_MAGIC;
 #endif
+	new->ucounts = get_ucounts(&init_ucounts);
 
 	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
@@ -284,6 +288,11 @@ struct cred *prepare_creds(void)
 
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
+
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	validate_creds(new);
 	return new;
 
@@ -351,7 +360,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		kdebug("share_creds(%p{%d,%d})",
 		       p->cred, atomic_read(&p->cred->usage),
 		       read_cred_subscribers(p->cred));
-		atomic_inc(&p->cred->user->processes);
+		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
 	}
 
@@ -363,6 +372,9 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		ret = create_user_ns(new);
 		if (ret < 0)
 			goto error_put;
+		ret = set_cred_ucounts(new);
+		if (ret < 0)
+			goto error_put;
 	}
 
 #ifdef CONFIG_KEYS
@@ -384,8 +396,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	}
 #endif
 
-	atomic_inc(&new->user->processes);
 	p->cred = p->real_cred = get_cred(new);
+	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 	alter_cred_subscribers(new, 2);
 	validate_creds(new);
 	return 0;
@@ -485,12 +497,12 @@ int commit_creds(struct cred *new)
 	 * in set_user().
 	 */
 	alter_cred_subscribers(new, 2);
-	if (new->user != old->user)
-		atomic_inc(&new->user->processes);
+	if (new->user != old->user || new->user_ns != old->user_ns)
+		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user)
-		atomic_dec(&old->user->processes);
+		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
@@ -653,6 +665,31 @@ int cred_fscmp(const struct cred *a, const struct cred *b)
 }
 EXPORT_SYMBOL(cred_fscmp);
 
+int set_cred_ucounts(struct cred *new)
+{
+	struct task_struct *task = current;
+	const struct cred *old = task->real_cred;
+	struct ucounts *old_ucounts = new->ucounts;
+
+	if (new->user == old->user && new->user_ns == old->user_ns)
+		return 0;
+
+	/*
+	 * This optimization is needed because alloc_ucounts() uses locks
+	 * for table lookups.
+	 */
+	if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid))
+		return 0;
+
+	if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid)))
+		return -EAGAIN;
+
+	if (old_ucounts)
+		put_ucounts(old_ucounts);
+
+	return 0;
+}
+
 /*
  * initialise the credentials stuff
  */
@@ -719,6 +756,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	put_cred(old);
 	validate_creds(new);
 	return new;